© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 31504
    Prev
    Next
    INDEX
    Explanations

    in order to followed by verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    '
    1.42
    m
    1.41
    ending
    1.34
    ’
    1.33
    ↵
    1.29
    mounted
    1.29
    }
    1.25
    uras
    1.24
    aka
    1.22
    wind
    1.21
    POSITIVE LOGITS
    יים
    1.67
     Zanz
    1.56
    龰
    1.55
    ます
    1.55
    ますが
    1.55
    穸
    1.53
    𝙋
    1.53
    玴
    1.52
    絟
    1.50
    मी
    1.48
    Activations Density 0.014%

    No Known Activations